Unsupervised Representation Learning - an Invariant Risk Minimization Perspective

Yotam Norman, Ron Meir

Keywords: Unsupervised Learning, Invariant Risk Minimization, Variational Autoencoder, Principal Components Analysis

TL;DR: We propose and study Invariant Risk Minimization (IRM) in the context of unsupervised learning

Abstract: We propose a novel unsupervised framework for Invariant Risk Minimization (IRM), extending the concept of invariance to settings where labels are unavailable. Traditional IRM methods rely on labeled data to learn representations that are robust to distributional shifts across environments. In contrast, our approach redefines invariance through feature distribution alignment, enabling robust representation learning from unlabeled data. We introduce two methods within this framework: Principal Invariant Component Analysis (PICA), a linear method that extracts invariant directions under Gaussian assumptions, and Variational Invariant Autoencoder (VIAE), a deep generative model that separates environment-invariant and environment-dependent latent factors. Our approach is based on a novel ``unsupervised'' structural causal model and supports environment-conditioned sample-generation and intervention. Empirical evaluations on synthetic dataset, modified versions of MNIST, and CelebA demonstrate the effectiveness of our methods in capturing invariant structure, preserving relevant information, and generalizing across environments without access to labels.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Submission Number: 3408